True Meeting Inc.

Cavendish Capital LLC

Wochit Inc.

Ran Oz

Yuval Gronau

Osnat Goren-Peyser

Tal Perl

Michael Rabinovich

Erez Posner

Amir Bassan-Eskenazi

Amotz Hoshen

Nery Strasman

Omri Kaduri

Dror Ginzberg

Eitan Lavi

Ran Yakir

Ron Maayan

Eyal Gavish

Rima Gandlin

Omri Gandlin

Igor Dvorkin

Yuval Spiegel

A method for video conference environment generation, the method may include detecting a participant gaze pattern in relation to a display that displays a version of a virtual three dimensional virtual 3D video conference environment video conference environment (V3DVCE); and changing, without an explicit request from the participant, one or more display parameters of the V3DVCE to induce a change of at least one participant gaze pattern parameter.

Manipulating a virtual video conference environment

A method for creating a variable model of a face of a person, the method comprises: obtaining a non-riggable model of the face of the person; performing a first approximation process that comprises generating an intermediate variable model that approximates the non-riggable model, using an interactive variable model infrastructure; wherein the generating comprises iteratively changing shape parameters of the intermediate model until fulfilling a proximity condition; and performing a second approximation process that comprises generating the variable model, by iteratively modifying vertices.

Method for creating a variable model of a face of a person

A method for generating alpha channel information related to a person, the method may include generating the alpha channel information related to the person by an alpha channel neural network; wherein the alpha channel machine learning process is trained using ground truth alpha channel information that is associated with background information; wherein the ground-truth alpha channel information is generated by: obtaining input images of the person; wherein each image comprises the person and an arbitrary background; repeating, for each input image of the input images, converting the input image, by a portrait matting predictor, to (a) a first colored background image that comprises the person and a background of a first color, and (b) a second colored background image that comprises the person and a background of a second color; wherein the first color differs from the second color.

Generating an alpha channel

A method for creating a non-riggable model of a face of a person, the method includes obtaining video and depth information regarding the face of the person, wherein different images of the video are acquired by a camera at different camera locations; and for each image of the different images repeating the steps of: separating face information from background information; determining translation and rotation parameters that represent the different camera locations; and generating the non-riggable model of the face of the person based on the face information and the translation and rotation parameters.

Creating a non-riggable model of a face of a person

A method for updating a current three dimensional (3D) model of a person, that method may include calculating current locations, within a two-dimensional (2D) space, of current face landmark points of a face of a person within a first image; the calculating is based on the current 3D model, and one or more current acquisition parameters of a 2D camera; wherein the current 3D model of the person is located within a 3D space; calculating second locations, within the 2D space, of second face landmark points of the face of the person within a second image that follows the first image; calculating correspondences between the current locations and the second locations; calculating, based on the correspondences, locations of the second face landmark points within the 3D space; and modifying the current 3D model based on the locations of the second face landmark points within the 3D space.

Updating 3D models of persons

A method for virtually mimicking an arm movement of participant of a three dimensional (3D) video conference, the method may include (i) obtaining joints movement information about joints movements of an arm of a participant of the 3D video conference, based on a movement of the arm of the participant that was captured by a video taken by a camera of the participant, wherein arm of the participant is free of physical joint movement markers; (ii) generating, an arm skeletal model that represents the joins movement of the arm, based on the joints movement information; (iii) generating, by a machine learning process, a renderable 3D model of the arm that mimics the movement of the arm of the participant; and (iv) responding to the generating of the renderable 3D model, wherein the responding comprises at least one out of (a) rendering an avatar of the participant based on the renderable 3D model, (b) storing renderable 3D model information, or (c) sending the renderable 3D model information to another computerized device related to the 3D video conference.

Arm movement mimicking

A method for conducting a three dimensional (3D) video conference between multiple participants, the method may include acquiring visual information, by a visual sensing unit related to a certain participant; identifying multiple persons that appear in the visual information; finding, out of the multiple persons, at least one relevant person; determining 3D entity representation information, for each of the at least one relevant person; and generating, for at least one participant, a representation of a virtual 3D video conference environment, based on the 3D entity representation information for each of the at least one relevant person.

Method and system for virtual 3D communications having multiple participants per camera

A method for generating a texture map used during a video conference, the method may include obtaining multiple texture maps of multiple areas of at least a portion of a three-dimensional (3D) object in which the multiple texture maps comprise a first texture map of a first area and of a first resolution, and a second texture map of a second area and of a second resolution, in which the first area differs from the second area and the first resolution differs from the second resolution; generating a texture map of the at least portion of the 3D object. The generating is based on the multiple texture maps; and utilizing the visual representation of the at least portion of the 3D object based on the texture map of the at least portion of the 3D object during the video conference.

3D video conferencing

A method for avatar virtual arm movement, the method may include (i) capturing, by a camera of a participant of a video conference, a hand gesture made by the participant without capturing an arm movement of the participant, the arm movement is associated with the hand gesture; (ii) determining the arm movement of the participant, based on the hand gesture; (iii) determining a virtual movement of an arm of an avatar of the participant within a virtual video conference environment, the virtual movement of the arm of the avatar of the participant mimics the arm movement of the participant; and (iv) assisting to perform the virtual arm movement of the avatar within the virtual video conference environment.

Avatar virtual arm movement

A method for conducting a three dimensional (3D) video conference with multiple participants, the method may include (i) receiving, from a first participant and by software used to conduct the 3D video conference call, a request to see a second avatar that represents a second participant, within a representation of a virtual 3D environment displayed to the first participant during the 3D video conference; (ii) displaying the second avatar within the representation following a reception of (a) a first approval from the software to display the avatar within the representation, and (b) a second participant approval to display the avatar within the representation; and (iii) avoiding from displaying the second avatar within the representation until receiving the first approval and the second participant approval.

Avatar information protection

A method for audio quality improvement related to a participant of a virtual three dimensional (3D) video conference, the method may include: determining participant generated audio, by a machine learning process and based on image analysis of a video of the participant obtained during the virtual 3D video conference; and generating participant related audio information based at least on the participant generated audio; wherein the participant related audio information, once provided to a computerized system of another participant, causes the computerized system of the other participant to generate participant related audio of higher quality than participant audio when the participant audio is included in sensed audio that is sensed by an audio sensor that is associated with the participant.

Audio quality improvement related to a participant of a virtual three dimensional (3D) video conference

A method for virtual 3D video conference environment generation, the method may include (a) determining a first optical axis of a first virtual camera, the first optical axis represents a line of sight of the participant while a participant of the 3D video conference environment looks at a current displayed version of a virtual 3D video conference environment (V3DVCE); the current displayed version of the V3DVCE is displayed on a display; (b) determining a second optical axis of a second virtual camera that virtually captures the V3DVCE to provide the current displayed version of the V3DVCE; and (c) generating a next displayed version of the V3DVCE based on at least one of the first optical axis and the second optical axis.

Virtual 3D video conference environment generation

A method for conducting a three dimensional (3D) video conference between multiple participants, the method may include receiving initial 3D participant representation information for generating the 3D representation of the participant under different circumstances; receiving, by a user device of a first participant and during the 3D video conference call, second participant circumstances metadata indicative of one or more current circumstances regarding a second participant; and updating, by the user device of the first participant, a 3D participant representation of the second participant, within a first representation of virtual 3D video conference environment.

Circumstances based 3D representations of participants of virtual 3D communications

A method for sharing content during a virtual 3D video conference, the method may include inviting multiple participants to join a virtual 3D video conference; creating a shared folder dedicated for storing shared content items, wherein the shared content is accessible during at least during the virtual 3D video conference; enabling access, to the multiple participants, to the shared folder; wherein the access is governed by one or more access control rule; and conducting the virtual 3D video conference; wherein the conducting comprises sharing at least one of the content items.

Sharing content during a virtual 3D video conference

A method for foreground and background segmentation related to a virtual three-dimensional (3D) video conference, the method may include segmenting each image of multiple images of a video stream, to segments, each segment has one or more properties that are constant; determining temporal properties of the segments; and classifying each segment as a background segment or a foreground segment, based at least in part, on the temporal properties of the segments.

Growing community of inventors

Maccabim, Israel

Ran Oz